Expressway traffic monitoring method and system and medium
Through the collaborative architecture of edge computing nodes and data extraction nodes, the problems of insufficient multi-source heterogeneous data fusion capabilities and response delays in highway traffic monitoring systems are solved, and real-time and accurate traffic monitoring is achieved.
Patent Information
- Application Number
- CN202510917399.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-03
- Publication Date
- 2025-09-19
AI Technical Summary
The existing highway traffic monitoring system lacks the ability to integrate multi-source heterogeneous data, and the centralized computing architecture leads to severe response delays, which cannot meet real-time decision-making needs.
It adopts a collaborative architecture of edge computing nodes and data extraction nodes, acquires and preprocesses multi-source heterogeneous data, combines external influencing data, realizes distributed computing and real-time data processing, and uses preset associations to accurately schedule data and computing power.
It improves the ability to integrate multi-source heterogeneous data, reduces data transmission delays, achieves response times in seconds, reduces the bandwidth pressure on central servers, and meets real-time monitoring needs.
Smart Images
Figure CN120673600A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of traffic monitoring technology, and in particular to a method, system and medium for monitoring highway traffic. Background Art
[0002] Current highway traffic monitoring primarily utilizes a technical solution that combines traditional IoT architecture with rule-based analysis. Existing technologies typically collect basic traffic flow data through fixed sensors (such as geomagnetic coils and microwave radar), combined with video surveillance systems for manual patrols or simple image recognition (such as license plate capture and congestion detection). Data processing typically utilizes a centralized cloud computing model, transmitting raw data collected from various road sections to a central server for unified analysis. Event judgment relies on pre-set threshold rules (such as a vehicle speed below 20 km / h triggering a congestion alert) or traditional machine learning models (such as support vector machine (SVM) classifiers). External influencing factors (such as meteorological data) are primarily accessed through independent subsystems and analyzed post-hoc with traffic data.
[0003] Existing technologies have the following defects: First, the ability to fuse multi-source heterogeneous data is insufficient, and the data standards of various subsystems are not unified (such as differences in video frame rate and sensor sampling frequency); second, the centralized computing architecture leads to serious response delays, and the end-to-end delay from data collection to warning output generally exceeds 5 minutes, which cannot meet real-time decision-making needs. Summary of the Invention
[0004] The present application provides a highway traffic monitoring method, system and medium to solve the problems of insufficient multi-source heterogeneous data fusion capabilities and severe response delays caused by centralized computing architecture in existing solutions.
[0005] In a first aspect, the present application provides a method for monitoring highway traffic, the method comprising: Acquire multi-source heterogeneous real-time data and external influence data; wherein, the multi-source heterogeneous real-time data at least includes: traffic flow detection data, video surveillance data, and mobile terminal uploaded data, and the external influence data at least includes meteorological data and road construction data; based on the traffic flow detection data, divide the highway into several sections to be detected; based on the video surveillance data, determine the monitoring type of each section to be detected; determine the monitoring data type and monitoring program of each monitoring type, send the monitoring data type to the corresponding data extraction node, and send the monitoring program to the corresponding edge computing node; wherein, there is a preset association relationship between the data extraction node and the edge computing node; through the data extraction node, extract specific data corresponding to the monitoring data type from the multi-source heterogeneous real-time data and external influence data; transmit the specific data to the corresponding edge computing node, input the monitoring program, and obtain the output monitoring result.
[0006] In one implementation of the present application, based on traffic flow detection data, the highway is divided into several sections to be detected, specifically including: Divide the highway into several initial sections according to the preset distance; According to the traffic flow detection data, the difference in flow between two adjacent initial road sections is detected; When the difference is less than the preset difference threshold, the two adjacent initial sections are merged into one section; When the difference is greater than or equal to the preset difference threshold, the two adjacent initial road sections are not merged; After all road sections are processed, the remaining road sections are determined to be road sections to be detected.
[0007] In one implementation of the present application, the monitoring type of each road section to be detected is determined based on the video monitoring data, specifically including: Read the video surveillance data, and determine the monitoring type of the current road section to be detected based on the ratio between preset small vehicles, preset medium vehicles, and preset large vehicles in the video surveillance data and the association between the preset ratio and the monitoring type.
[0008] In one implementation of the present application, determining the monitoring data type and monitoring procedure for each monitoring type specifically includes: Configure the relationship between monitoring type, monitoring data type and monitoring program through the preset interface; After determining the monitoring type, obtain the monitoring data type and monitoring program from the association relationship.
[0009] In one implementation of the present application, before sending the monitoring data type to the corresponding data extraction node and sending the monitoring program to the corresponding edge computing node, the method further includes: According to the specific location of the road section to be detected, the data extraction node closest to the current specific location is determined from a number of data extraction nodes as the data extraction node corresponding to the monitoring data type of the current road section to be detected; And determine from a number of edge computing nodes the edge computing node closest to the current specific location as the edge computing node corresponding to the monitoring program of the current road section to be detected.
[0010] In one implementation of the present application, specific data corresponding to the monitoring data type is extracted from multi-source heterogeneous real-time data and external impact data through a data extraction node, specifically including: Several multi-source heterogeneous parsing modules are configured at the data extraction node, and the multi-source heterogeneous parsing modules are used to extract specific data corresponding to the monitoring data type from multi-source heterogeneous real-time data and external impact data.
[0011] In a second aspect, the present application provides a highway traffic monitoring system, the system comprising: An acquisition module is used to acquire multi-source heterogeneous real-time data and external impact data; wherein the multi-source heterogeneous real-time data at least includes: traffic flow detection data, video surveillance data, and mobile terminal uploaded data; the external impact data at least includes meteorological data and road construction data; The determination module is used to divide the highway into several sections to be detected based on the traffic flow detection data; and determine the monitoring type of each section to be detected based on the video monitoring data; A sending module is used to determine the monitoring data type and monitoring program of each monitoring type, send the monitoring data type to the corresponding data extraction node, and send the monitoring program to the corresponding edge computing node; wherein the data extraction node and the edge computing node have a preset association relationship; The acquisition module is used to extract specific data corresponding to the monitoring data type from multi-source heterogeneous real-time data and external influence data through the data extraction node; transmit the specific data to the corresponding edge computing node, input the monitoring program, and obtain the output monitoring results.
[0012] In one implementation of the present application, the determination module includes a road segment determination unit, Used to divide the highway into several initial sections according to preset distances; According to the traffic flow detection data, the difference in flow between two adjacent initial road sections is detected; When the difference is less than the preset difference threshold, the two adjacent initial sections are merged into one section; When the difference is greater than or equal to the preset difference threshold, the two adjacent initial road sections are not merged; After all road sections are processed, the remaining road sections are determined to be road sections to be detected.
[0013] In one implementation of the present application, the determination module includes a type determination unit, It is used to read video surveillance data, and determine the monitoring type of the current road section to be detected based on the ratio between preset small vehicles, preset medium vehicles, and preset large vehicles in the video surveillance data and the association between the preset ratio and the monitoring type.
[0014] In a third aspect, the present application provides a non-volatile computer storage medium having computer instructions stored thereon, which, when executed, implement a highway traffic monitoring method as described above.
[0015] It can be seen from the above technical solutions that this application has the following advantages: 1. Improvement of multi-source heterogeneous data fusion capabilities: By integrating traffic flow monitoring data, video surveillance data, mobile terminal uploads, and external influence data such as weather and road construction, the system achieves structured collection of comprehensive highway information. This technical solution addresses the issues of inconsistent data formats and semantic gaps inherent in traditional solutions through a targeted matching mechanism between "data extraction nodes" and "monitoring data types." The introduction of large models further enhances the ability to analyze unstructured video data, for example, automatically labeling accident types or congestion levels through visual recognition. This multimodal data fusion capability transcends the one-sided judgments of a single data source and instead forms a comprehensive decision-making framework based on environmental factors, real-time road conditions, and historical patterns.
[0016] 2. Real-time breakthroughs brought by distributed computing architecture: Adopting a collaborative architecture of "edge computing nodes + data extraction nodes," the system breaks down traditional centralized monitoring tasks into parallel computations at the road section level. The technical solution establishes precise scheduling channels for data and computing power through pre-set relationships, enabling rapid integration of global information, such as meteorological data, with video analysis tasks for specific road sections at the edge. The monitoring program's delivery mechanism enables dynamic allocation of computing resources, preventing system-wide computing power overload caused by sudden accidents on a particular road section. This architectural design reduces data transmission latency, shortening response times for critical scenarios such as construction warnings and accident detection from minutes to seconds, while also reducing bandwidth pressure on central servers. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0018] Figure 1 This is a flow chart of a highway traffic monitoring method provided in an embodiment of the present application.
[0019] Figure 2 This is a schematic diagram of the internal structure of a highway traffic monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0021] It should be understood by those skilled in the art that the embodiments described below are merely preferred embodiments of the present disclosure and do not imply that the present disclosure can only be implemented through these preferred embodiments. These preferred embodiments are merely intended to explain the technical principles of the present disclosure and are not intended to limit the scope of protection of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of the present disclosure.
[0022] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.
[0023] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0024] The embodiment provides a method for monitoring highway traffic. Figure 1 As shown, the method provided in the embodiment of the present application mainly includes the following steps: Step 110: Acquire multi-source heterogeneous real-time data and external impact data.
[0025] Among them, multi-source heterogeneous real-time data at least includes: traffic flow detection data, video surveillance data, and mobile terminal uploaded data; external impact data at least includes meteorological data and road construction data.
[0026] It should be noted that this step simultaneously acquires three types of real-time data: traffic flow measurement data, video surveillance data, and mobile terminal upload data. Combined with external influence data such as weather and road construction, this step constructs a multi-dimensional traffic situation awareness system. This benefit is reflected in three aspects: First, the parallel collection of multi-source heterogeneous data overcomes the limitations of traditional single-sensor monitoring. For example, a geomagnetic coil detector only provides traffic flow data. This step supplements vehicle type identification with video data and captures individual trajectories with mobile terminal data, forming a foundation for macro- and micro-level analysis. Second, the proactive inclusion of external influence data establishes a correlation model between environmental factors and traffic conditions, enabling the system to predict the impact of weather changes on road capacity and plan traffic diversion strategies for construction sections in advance. Third, this data architecture provides standardized input for subsequent edge computing. Traffic flow data, as structured numerical values, can be directly used to calculate the congestion index. Pre-processed metadata annotation (such as vehicle coordinate frames) on video data reduces the parsing load on edge nodes. Desensitized mobile terminal data forms valid samples for OD (origin-destination) analysis.
[0027] Step 120: Divide the highway into several sections to be detected based on the traffic flow detection data; and determine the monitoring type of each section to be detected based on the video monitoring data.
[0028] Among them, based on the traffic flow detection data, the highway is divided into several sections to be detected, including: Divide the highway into several initial sections according to the preset distance; According to the traffic flow detection data, the difference in flow between two adjacent initial road sections is detected; When the difference is less than the preset difference threshold, the two adjacent initial sections are merged into one section; When the difference is greater than or equal to the preset difference threshold, the two adjacent initial road sections are not merged; After all road sections are processed, the remaining road sections are determined to be road sections to be detected.
[0029] Among them, according to the video surveillance data, the monitoring type of each road section to be detected is determined, including: Read the video surveillance data, and determine the monitoring type of the current road section to be detected based on the ratio between preset small vehicles, preset medium vehicles, and preset large vehicles in the video surveillance data and the association between the preset ratio and the monitoring type.
[0030] It should be noted that this step simultaneously acquires three types of real-time data: traffic flow measurement data, video surveillance data, and mobile terminal upload data. Combined with external influence data such as weather and road construction, this system builds a multi-dimensional traffic situation awareness system. Its beneficial effects are reflected in three aspects: First, the parallel collection of multi-source heterogeneous data overcomes the limitations of traditional single-sensor monitoring. For example, a geomagnetic coil detector only provides traffic flow data. This solution supplements vehicle type identification with video data and captures individual trajectories with mobile terminal data, forming a foundation for macro- and micro-level analysis. Second, the active inclusion of external influence data establishes a correlation model between environmental factors and traffic conditions, enabling the system to predict the impact of weather changes on road capacity and plan traffic diversion strategies for construction sections in advance. Third, this data architecture provides standardized input for subsequent edge computing. Traffic flow data, as structured numerical values, can be directly used to calculate the congestion index. Pre-processed metadata annotation (such as vehicle coordinate frames) on video data reduces the parsing load on edge nodes. Desensitized mobile terminal data forms valid samples for OD (origin-destination) analysis. This data acquisition mechanism avoids the additional overhead of later data alignment. All data sources are uniformly registered according to the spatiotemporal benchmark (such as UTC timestamp + road section stake number) during the collection phase, providing underlying support for multimodal data fusion.
[0031] Step 130: Determine the monitoring data type and monitoring program for each monitoring type, send the monitoring data type to the corresponding data extraction node, and send the monitoring program to the corresponding edge computing node.
[0032] Among them, there is a preset association relationship between the data extraction node and the edge computing node.
[0033] The monitoring data type and monitoring procedure of each monitoring type are determined, which may be: Configure the relationship between monitoring type, monitoring data type and monitoring program through the preset interface; After determining the monitoring type, obtain the monitoring data type and monitoring program from the association relationship.
[0034] Before sending the monitoring data type to the corresponding data extraction node and sending the monitoring program to the corresponding edge computing node, the method further includes: According to the specific location of the road section to be detected, the data extraction node closest to the current specific location is determined from a number of data extraction nodes as the data extraction node corresponding to the monitoring data type of the current road section to be detected; And determine from a number of edge computing nodes the edge computing node closest to the current specific location as the edge computing node corresponding to the monitoring program of the current road section to be detected.
[0035] It should be noted that this step, through an intelligent resource scheduling mechanism, precisely matches computing resources and data requirements within the highway monitoring system. Its key benefits are as follows: First, the preconfigured association model of "monitoring type-data type-processor" enables the system to automatically select the optimal processing solution based on actual traffic scenarios (e.g., high-accident sections require video analysis and license plate recognition), eliminating the lag inherent in manual configuration in traditional solutions. Second, a node selection algorithm based on geographic proximity (e.g., nodes within 300 meters are prioritized on the K125 section) reduces data transmission latency. Third, the pre-set association between data extraction nodes and edge computing nodes forms a processing pipeline, ensuring that extracted video metadata can be directly fed into the corresponding analysis program (e.g., extracted traffic density data can be directly fed into a congestion prediction model), reducing intermediate data transfer steps. This distributed architecture enables customized monitoring services for each road section—freight corridors focus on vehicle type recognition, toll booths strengthen violation detection, and conventional sections require only basic traffic statistics, improving overall system resource utilization. Finally, the pre-configured interface provides a visual interface for operations and maintenance personnel. Selecting the "fog monitoring" type from the drop-down menu automatically links meteorological data collection and visibility analysis programs, significantly lowering the technical deployment threshold. This entire mechanism ensures real-time response while dynamically optimizing the allocation of limited computing resources.
[0036] Step 140: Extract specific data corresponding to the monitoring data type from multi-source heterogeneous real-time data and external impact data through the data extraction node; transmit the specific data to the corresponding edge computing node, input the monitoring program, and obtain the output monitoring results.
[0037] In some embodiments, specific data corresponding to the monitoring data type is extracted from multi-source heterogeneous real-time data and external impact data through a data extraction node, specifically including: Several multi-source heterogeneous parsing modules are configured at the data extraction node, and the multi-source heterogeneous parsing modules are used to extract specific data corresponding to the monitoring data type from multi-source heterogeneous real-time data and external impact data.
[0038] It's important to note that this step establishes an efficient traffic monitoring data processing chain through the collaborative processing of modular data extraction and edge computing. Its core value lies in three aspects: First, the deployment of multi-source heterogeneous parsing modules enables precise data source filtering. For example, only the image frames required for license plate recognition (the 3rd, 5th, and 8th frames per second) are extracted from the video stream, and humidity indicators that affect visibility are filtered out from meteorological data. This targeted extraction reduces the amount of raw data. Second, the strict correspondence between data types and compute nodes ensures the integrity of the processing logic. When construction road occupation data is extracted, the edge node automatically triggers the lane reduction algorithm; when rain and snow data are detected, the slippery road warning model is activated, avoiding the context loss problem encountered in traditional centralized processing. Third, the preprocessing mechanism based on the parsing module significantly improves edge computing efficiency. After the video data is converted into structured metadata (such as "red car in the third lane of K125+500 northbound") by the parsing module, the edge node does not need to repeatedly decode the original video, reducing the average processing latency of each node.
[0039] In addition, this application Figure 2 A highway traffic monitoring system is provided in the embodiment of the present application. Figure 2 As shown, the system provided in the embodiment of the present application mainly includes: The acquisition module 210 is used to acquire multi-source heterogeneous real-time data and external impact data; wherein the multi-source heterogeneous real-time data at least includes: traffic flow detection data, video surveillance data, and mobile terminal uploaded data; the external impact data at least includes meteorological data and road construction data.
[0040] The determination module 220 is used to divide the highway into a number of sections to be detected based on the traffic flow detection data; and determine the monitoring type of each section to be detected based on the video monitoring data.
[0041] The determination module 220 includes a road segment determination unit, Used to divide the highway into several initial sections according to preset distances; According to the traffic flow detection data, the difference in flow between two adjacent initial road sections is detected; When the difference is less than the preset difference threshold, the two adjacent initial sections are merged into one section; When the difference is greater than or equal to the preset difference threshold, the two adjacent initial road sections are not merged; After all road sections are processed, the remaining road sections are determined to be road sections to be detected.
[0042] The determination module 220 includes a type determination unit, It is used to read video surveillance data, and determine the monitoring type of the current road section to be detected based on the ratio between preset small vehicles, preset medium vehicles, and preset large vehicles in the video surveillance data and the association between the preset ratio and the monitoring type.
[0043] The sending module 230 is used to determine the monitoring data type and monitoring program of each monitoring type, send the monitoring data type to the corresponding data extraction node, and send the monitoring program to the corresponding edge computing node; wherein, there is a preset association relationship between the data extraction node and the edge computing node.
[0044] It should be noted that the dispatch module 230 uses an intelligent resource scheduling mechanism to precisely match computing resources with data requirements within the highway monitoring system. Its core benefits are as follows: First, the preconfigured association model of "monitoring type-data type-processing program" enables the system to automatically select the optimal processing solution based on actual traffic scenarios (e.g., high-accident sections require video analysis and license plate recognition programs), eliminating the lag inherent in manual configuration in traditional solutions. Second, a node selection algorithm based on geographic proximity (e.g., nodes within 300 meters are prioritized on the K125 section) reduces data transmission latency. Third, the pre-set association between data extraction nodes and edge computing nodes forms a processing pipeline, ensuring that extracted video metadata can be directly fed into the corresponding analysis program (e.g., extracted traffic density data can be directly fed into a congestion prediction model), reducing intermediate data transfer steps. This distributed architecture enables customized monitoring services for each road section—freight corridors focus on vehicle type identification, toll booths strengthen violation detection, and conventional sections require only basic traffic statistics, improving overall system resource utilization. Finally, the pre-configured interface provides a visual interface for operations and maintenance personnel. Selecting the "fog monitoring" type from the drop-down menu automatically links meteorological data collection and visibility analysis programs, significantly lowering the technical deployment threshold. This entire mechanism ensures real-time response while dynamically optimizing the allocation of limited computing resources.
[0045] The acquisition module 240 is used to extract specific data corresponding to the monitoring data type from multi-source heterogeneous real-time data and external impact data through the data extraction node; transmit the specific data to the corresponding edge computing node, input the monitoring program, and obtain the output monitoring results.
[0046] It should be noted that acquisition module 240 establishes an efficient traffic monitoring data processing chain through the collaborative processing of modular data extraction and edge computing. Its core value lies in three aspects: First, the deployment of multi-source heterogeneous parsing modules enables precise data source screening. For example, only image frames required for license plate recognition (frames 3, 5, and 8 per second) are extracted from the video stream, and humidity indicators that affect visibility are filtered out from meteorological data. This targeted extraction reduces the amount of raw data. Second, the strict correspondence between data types and computing nodes ensures the integrity of the processing logic. When construction road occupation data is extracted, the edge node automatically triggers the lane reduction algorithm; when rain and snow data are detected, the slippery road warning model is activated, avoiding the context loss problem encountered in traditional centralized processing. Third, the preprocessing mechanism based on the parsing module significantly improves edge computing efficiency. After the video data is converted into structured metadata (such as "red car in the third lane of K125+500 northbound") by the parsing module, the edge node does not need to repeatedly decode the original video, reducing the average processing latency of each node.
[0047] In addition, an embodiment of the present application further provides a non-volatile computer storage medium on which executable instructions are stored. When the executable instructions are executed, a highway traffic monitoring method as described above is implemented.
[0048] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A highway traffic monitoring method, characterized in that: The method comprises: Acquire multi-source heterogeneous real-time data and external impact data; wherein the multi-source heterogeneous real-time data includes at least: traffic flow detection data, video surveillance data, and mobile terminal uploaded data; external impact data includes at least meteorological data and road construction data; Based on traffic flow detection data, the highway is divided into several sections to be detected; based on video surveillance data, the monitoring type of each section to be detected is determined; Determine the monitoring data type and monitoring program for each monitoring type, send the monitoring data type to the corresponding data extraction node, and send the monitoring program to the corresponding edge computing node; wherein the data extraction node and the edge computing node have a preset association relationship; Through the data extraction node, specific data corresponding to the monitoring data type is extracted from multi-source heterogeneous real-time data and external impact data; the specific data is transmitted to the corresponding edge computing node, input into the monitoring program, and the output monitoring results are obtained.
2. The highway traffic monitoring method according to claim 1, characterized in that: Based on the traffic flow detection data, the highway is divided into several sections to be detected, including: Divide the highway into several initial sections according to the preset distance; According to the traffic flow detection data, the difference in flow between two adjacent initial road sections is detected; When the difference is less than the preset difference threshold, the two adjacent initial sections are merged into one section; When the difference is greater than or equal to the preset difference threshold, the two adjacent initial road sections are not merged; After all road sections are processed, the remaining road sections are determined to be road sections to be detected.
3. The highway traffic monitoring method according to claim 1, characterized in that: Based on the video surveillance data, determine the monitoring type of each road section to be inspected, including: Read the video surveillance data, and determine the monitoring type of the current road section to be detected based on the ratio between preset small vehicles, preset medium vehicles, and preset large vehicles in the video surveillance data and the association between the preset ratio and the monitoring type.
4. The highway traffic monitoring method according to claim 1, characterized in that: Determine the monitoring data types and monitoring procedures for each monitoring type, including: Configure the relationship between monitoring type, monitoring data type and monitoring program through the preset interface; After determining the monitoring type, obtain the monitoring data type and monitoring program from the association relationship.
5. The highway traffic monitoring method according to claim 1, characterized in that: Before sending the monitoring data type to the corresponding data extraction node and sending the monitoring program to the corresponding edge computing node, the method further includes: According to the specific location of the road section to be detected, the data extraction node closest to the current specific location is determined from a number of data extraction nodes as the data extraction node corresponding to the monitoring data type of the current road section to be detected; And determine from a number of edge computing nodes the edge computing node closest to the current specific location as the edge computing node corresponding to the monitoring program of the current road section to be detected.
6. The highway traffic monitoring method according to claim 1, characterized in that: Through the data extraction node, specific data corresponding to the monitoring data type is extracted from multi-source heterogeneous real-time data and external impact data, including: Several multi-source heterogeneous parsing modules are configured at the data extraction node, and the multi-source heterogeneous parsing modules are used to extract specific data corresponding to the monitoring data type from multi-source heterogeneous real-time data and external impact data.
7. A highway traffic monitoring system, characterized in that: The system comprises: An acquisition module is used to acquire multi-source heterogeneous real-time data and external impact data; wherein the multi-source heterogeneous real-time data at least includes: traffic flow detection data, video surveillance data, and mobile terminal uploaded data; the external impact data at least includes meteorological data and road construction data; The determination module is used to divide the highway into several sections to be detected based on the traffic flow detection data; and determine the monitoring type of each section to be detected based on the video monitoring data; A sending module is used to determine the monitoring data type and monitoring program of each monitoring type, send the monitoring data type to the corresponding data extraction node, and send the monitoring program to the corresponding edge computing node; wherein the data extraction node and the edge computing node have a preset association relationship; The acquisition module is used to extract specific data corresponding to the monitoring data type from multi-source heterogeneous real-time data and external influence data through the data extraction node; transmit the specific data to the corresponding edge computing node, input the monitoring program, and obtain the output monitoring results.
8. The highway traffic monitoring system according to claim 7, characterized in that: The determination module includes a road section determination unit, Used to divide the highway into several initial sections according to preset distances; According to the traffic flow detection data, the difference in flow between two adjacent initial road sections is detected; When the difference is less than the preset difference threshold, the two adjacent initial sections are merged into one section; When the difference is greater than or equal to the preset difference threshold, the two adjacent initial road sections are not merged; After all road sections are processed, the remaining road sections are determined to be road sections to be detected.
9. The highway traffic monitoring system according to claim 7, characterized in that: The determination module includes a type determination unit, It is used to read video surveillance data, and determine the monitoring type of the current road section to be detected based on the ratio between preset small vehicles, preset medium vehicles, and preset large vehicles in the video surveillance data and the association between the preset ratio and the monitoring type.
10. A non-volatile computer storage medium, characterized in that Computer instructions are stored thereon, and when the computer instructions are executed, a highway traffic monitoring method according to any one of claims 1 to 6 is implemented.